The SubCons webserver: A user friendly web interface for state‐of‐the‐art subcellular localization prediction

Salvatore, Marco; Shu, Nanjiang; Elofsson, Arne

doi:10.1002/pro.3297

Cited by 14 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CAFA3 targets were used to perform a comparative benchmark among different prediction tools including BUSCA, two recently developed methods, namely the ensemble method SubCons ( 22 , 23 ) and DeepLoc ( 24 ), based on deep-learning, as well as LocTree3 ( 17 ) and Cello2.5 ( 25 ). All methods run using the respective web servers and their predictions are scored at the level of individual compartments using the Matthews Correlation Coefficient (MCC) (see the Performance evaluation section).…”

Section: Resultsmentioning

confidence: 99%

BUSCA: an integrative web server to predict subcellular localization of proteins

Savojardo

Martelli

Fariselli

et al. 2018

Nucleic Acids Research

331

206

View full text Add to dashboard Cite

Here, we present BUSCA (http://busca.biocomp.unibo.it), a novel web server that integrates different computational tools for predicting protein subcellular localization. BUSCA combines methods for identifying signal and transit peptides (DeepSig and TPpred3), GPI-anchors (PredGPI) and transmembrane domains (ENSEMBLE3.0 and BetAware) with tools for discriminating subcellular localization of both globular and membrane proteins (BaCelLo, MemLoci and SChloro). Outcomes from the different tools are processed and integrated for annotating subcellular localization of both eukaryotic and bacterial protein sequences. We benchmark BUSCA against protein targets derived from recent CAFA experiments and other specific data sets, reporting performance at the state-of-the-art. BUSCA scores better than all other evaluated methods on 2732 targets from CAFA2, with a F1 value equal to 0.49 and among the best methods when predicting targets from CAFA3. We propose BUSCA as an integrated and accurate resource for the annotation of protein subcellular localization.

show abstract

Section: Resultsmentioning

confidence: 99%

BUSCA: an integrative web server to predict subcellular localization of proteins

Savojardo

Martelli

Fariselli

et al. 2018

Nucleic Acids Research

331

206

View full text Add to dashboard Cite

show abstract

“…Since the functions of an apoptosis protein are closely related to its subcellular location and different kinds of apoptosis proteins can only function in specific subcellular location, it is important to predict the subcellular location of certain apoptosis protein by existing methods, which could not only help us to understand the interactions and properties of apoptosis proteins but also realize the biological pathway involved [1–3]. With the application of high-throughput sequencing techniques and the explosion of sequence data volumes, developing an accurate and reliable computational method to predict apoptosis protein subcellular location has been a great challenge for bioinformaticians, accordingly promoting the development of machine learning in this field [4–8].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Apoptosis Protein Subcellular Localization with Multilayer Sparse Coding and Oversampling Approach

Chen

et al. 2019

BioMed Research International

View full text Add to dashboard Cite

The prediction of apoptosis protein subcellular localization plays an important role in understanding the progress in cell proliferation and death. Recently computational approaches to this issue have become very popular, since the traditional biological experiments are so costly and time-consuming that they cannot catch up with the growth rate of sequence data anymore. In order to improve the prediction accuracy of apoptosis protein subcellular localization, we proposed a sparse coding method combined with traditional feature extraction algorithm to complete the sparse representation of apoptosis protein sequences, using multilayer pooling based on different sizes of dictionaries to integrate the processed features, as well as oversampling approach to decrease the influences caused by unbalanced data sets. Then the extracted features were input to a support vector machine to predict the subcellular localization of the apoptosis protein. The experiment results obtained by Jackknife test on two benchmark data sets indicate that our method can significantly improve the accuracy of the apoptosis protein subcellular localization prediction.

show abstract

“…2017 ), PProwler 1.2 (http://bioinf.scmb.uq.edu.au:8080/pprowler_webapp_1-2/; last accessed July 1, 2020) ( Hawkins and Bodén 2006 ), PTS1 predictor ( http://mendel.imp.ac.at/pts1/ ; last accessed July 1, 2020) ( Neuberger et al. 2003 ), Subcons ( http://subcons.bioinfo.se/ ; last accessed July 1, 2020) ( Salvatore et al. 2018 ), and SignalP-5.0 (https://services.healthtech.dtu.dk/service.php?SignalP-5.0; last accessed July 1, 2020) ( Almagro Armenteros et al.…”

Section: Methodsmentioning

confidence: 99%

Ultrastructural, Cytochemical, and Comparative Genomic Evidence of Peroxisomes in Three Genera of Pathogenic Free-Living Amoebae, Including the First Morphological Data for the Presence of This Organelle in Heteroloboseans

González‐Robles

González‐Lázaro

Lagunes-Guillén

et al. 2020

Genome Biology and Evolution

View full text Add to dashboard Cite

Abstract Peroxisomes perform various metabolic processes that are primarily related to the elimination of reactive oxygen species and oxidative lipid metabolism. These organelles are present in all major eukaryotic lineages, nevertheless, information regarding the presence of peroxisomes in opportunistic parasitic protozoa is scarce and in many cases it is still unknown whether these organisms have peroxisomes at all. Here, we performed ultrastructural, cytochemical and bioinformatic studies to investigate the presence of peroxisomes in three genera of free-living amoebae from two different taxonomic groups that are known to cause fatal infections in humans. By transmission electron microscopy, round structures with a granular content limited by a single membrane were observed in Acanthamoeba castellanii, Acanthamoeba griffini, Acanthamoeba polyphaga, Acanthamoeba royreba, Balamuthia mandrillaris (Amoebozoa) and Naegleria fowleri (Heterolobosea). Further confirmation for the presence of peroxisomes was obtained by treating trophozoites in situ with diaminobenzidine and hydrogen peroxide, which showed positive reaction products for the presence of catalase. We then performed comparative genomic analyses to identify predicted peroxin homologues in these organisms. Our results demonstrate that a complete set of peroxins -which are essential for peroxisome biogenesis, proliferation and protein import- are present in all of these amoebae. Likewise, our in silico analyses allowed us to identify a complete set of peroxins in Naegleria lovaniensis and three novel peroxin homologues in Naegleria gruberi. Thus, our results indicate that peroxisomes are present in these three genera of free-living amoebae and that they have a similar peroxin complement despite belonging to different evolutionary lineages.

show abstract

The SubCons webserver: A user friendly web interface for state‐of‐the‐art subcellular localization prediction

Cited by 14 publications

References 33 publications

BUSCA: an integrative web server to predict subcellular localization of proteins

BUSCA: an integrative web server to predict subcellular localization of proteins

Prediction of Apoptosis Protein Subcellular Localization with Multilayer Sparse Coding and Oversampling Approach

Ultrastructural, Cytochemical, and Comparative Genomic Evidence of Peroxisomes in Three Genera of Pathogenic Free-Living Amoebae, Including the First Morphological Data for the Presence of This Organelle in Heteroloboseans

Contact Info

Product

Resources

About